aboutsummaryrefslogtreecommitdiffstats
path: root/Documentation
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-08-01 12:02:41 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2012-08-01 12:02:41 -0400
commit8cf1a3fce0b95050b63d451c9d561da0da2aa4d6 (patch)
tree0dc7f93474c3be601a5893900db1418dfd60ba5d /Documentation
parentfcff06c438b60f415af5983efe92811d6aa02ad1 (diff)
parent80799fbb7d10c30df78015b3fa21f7ffcfc0eb2c (diff)
Merge branch 'for-3.6/core' of git://git.kernel.dk/linux-block
Pull core block IO bits from Jens Axboe: "The most complicated part if this is the request allocation rework by Tejun, which has been queued up for a long time and has been in for-next ditto as well. There are a few commits from yesterday and today, mostly trivial and obvious fixes. So I'm pretty confident that it is sound. It's also smaller than usual." * 'for-3.6/core' of git://git.kernel.dk/linux-block: block: remove dead func declaration block: add partition resize function to blkpg ioctl block: uninitialized ioc->nr_tasks triggers WARN_ON block: do not artificially constrain max_sectors for stacking drivers blkcg: implement per-blkg request allocation block: prepare for multiple request_lists block: add q->nr_rqs[] and move q->rq.elvpriv to q->nr_rqs_elvpriv blkcg: inline bio_blkcg() and friends block: allocate io_context upfront block: refactor get_request[_wait]() block: drop custom queue draining used by scsi_transport_{iscsi|fc} mempool: add @gfp_mask to mempool_create_node() blkcg: make root blkcg allocation use %GFP_KERNEL blkcg: __blkg_lookup_create() doesn't need radix preload
Diffstat (limited to 'Documentation')
-rw-r--r--Documentation/block/queue-sysfs.txt7
1 files changed, 7 insertions, 0 deletions
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index d8147b336c35..6518a55273e7 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -38,6 +38,13 @@ read or write requests. Note that the total allocated number may be twice
38this amount, since it applies only to reads or writes (not the accumulated 38this amount, since it applies only to reads or writes (not the accumulated
39sum). 39sum).
40 40
41To avoid priority inversion through request starvation, a request
42queue maintains a separate request pool per each cgroup when
43CONFIG_BLK_CGROUP is enabled, and this parameter applies to each such
44per-block-cgroup request pool. IOW, if there are N block cgroups,
45each request queue may have upto N request pools, each independently
46regulated by nr_requests.
47
41read_ahead_kb (RW) 48read_ahead_kb (RW)
42------------------ 49------------------
43Maximum number of kilobytes to read-ahead for filesystems on this block 50Maximum number of kilobytes to read-ahead for filesystems on this block